{"id":"https://openalex.org/W7165692668","doi":"https://doi.org/10.1186/s12859-026-06448-6","title":"FeSseqdb: a curated sequence-level database and interpretable machine learning framework for identifying iron\u2013sulfur proteins","display_name":"FeSseqdb: a curated sequence-level database and interpretable machine learning framework for identifying iron\u2013sulfur proteins","publication_year":2026,"publication_date":"2026-06-23","ids":{"openalex":"https://openalex.org/W7165692668","doi":"https://doi.org/10.1186/s12859-026-06448-6","pmid":"https://pubmed.ncbi.nlm.nih.gov/42337419"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-026-06448-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06448-6","pdf_url":"https://link.springer.com/content/pdf/10.1186/s12859-026-06448-6.pdf","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1186/s12859-026-06448-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008051623","display_name":"Jiyeon Min","orcid":"https://orcid.org/0009-0006-8086-095X"},"institutions":[{"id":"https://openalex.org/I4210106489","display_name":"National Heart Lung and Blood Institute","ror":"https://ror.org/012pb6c26","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210106489"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiyeon Min","raw_affiliation_strings":["Biophysics Program, Institute for Physical Science and Technology, University of Maryland, College Park, MD, 20742, USA. jmin7@umd.edu","Laboratory of Computational Biology, National Heart, Lung, and Blood Institute, National Institutes of Health, Bethesda, MD, 20892, USA. jmin7@umd.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biophysics Program, Institute for Physical Science and Technology, University of Maryland, College Park, MD, 20742, USA. jmin7@umd.edu","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Laboratory of Computational Biology, National Heart, Lung, and Blood Institute, National Institutes of Health, Bethesda, MD, 20892, USA. jmin7@umd.edu","institution_ids":["https://openalex.org/I4210106489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136075371","display_name":"Bernard R. Brooks","orcid":null},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210106489","display_name":"National Heart Lung and Blood Institute","ror":"https://ror.org/012pb6c26","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210106489"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bernard R. Brooks","raw_affiliation_strings":["Laboratory of Computational Biology, National Heart, Lung, and Blood Institute, National Institutes of Health, Bethesda, MD, 20892, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Computational Biology, National Heart, Lung, and Blood Institute, National Institutes of Health, Bethesda, MD, 20892, USA","institution_ids":["https://openalex.org/I4210106489","https://openalex.org/I1299303238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018180963","display_name":"Muhamed Amin","orcid":"https://orcid.org/0000-0002-3146-150X"},"institutions":[{"id":"https://openalex.org/I4210106489","display_name":"National Heart Lung and Blood Institute","ror":"https://ror.org/012pb6c26","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210106489"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Muhamed Amin","raw_affiliation_strings":["Laboratory of Computational Biology, National Heart, Lung, and Blood Institute, National Institutes of Health, Bethesda, MD, 20892, USA. muhamed.amin@nih.gov"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Computational Biology, National Heart, Lung, and Blood Institute, National Institutes of Health, Bethesda, MD, 20892, USA. muhamed.amin@nih.gov","institution_ids":["https://openalex.org/I4210106489"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008051623","https://openalex.org/A5018180963"],"corresponding_institution_ids":["https://openalex.org/I4210106489","https://openalex.org/I66946132"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74720125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11626","display_name":"Metalloenzymes and iron-sulfur proteins","score":0.840399980545044,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11626","display_name":"Metalloenzymes and iron-sulfur proteins","score":0.840399980545044,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11297","display_name":"Ferroptosis and cancer prognosis","score":0.013899999670684338,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12149","display_name":"Nanocluster Synthesis and Applications","score":0.009999999776482582,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.4300000071525574},{"id":"https://openalex.org/keywords/database-query","display_name":"Database query","score":0.296099990606308},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.28189998865127563},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2703999876976013}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7073000073432922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5580000281333923},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4587000012397766},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.4300000071525574},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.40149998664855957},{"id":"https://openalex.org/C2989070954","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database query","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2856999933719635},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2628999948501587},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.25600001215934753}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007506","descriptor_name":"Iron-Sulfur Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-026-06448-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06448-6","pdf_url":"https://link.springer.com/content/pdf/10.1186/s12859-026-06448-6.pdf","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:42337419","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42337419","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:b83f834f0f5849dcb094565f4965d508","is_oa":false,"landing_page_url":"https://doaj.org/article/b83f834f0f5849dcb094565f4965d508","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 27, Iss 1 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13292568","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13292568/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-026-06448-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06448-6","pdf_url":"https://link.springer.com/content/pdf/10.1186/s12859-026-06448-6.pdf","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337338","display_name":"National Heart, Lung, and Blood Institute","ror":"https://ror.org/012pb6c26"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7165692668.pdf","grobid_xml":"https://content.openalex.org/works/W7165692668.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1480132160","https://openalex.org/W1965784004","https://openalex.org/W1973530249","https://openalex.org/W1974086171","https://openalex.org/W1975915682","https://openalex.org/W1980227664","https://openalex.org/W1992176190","https://openalex.org/W1995511619","https://openalex.org/W2004538890","https://openalex.org/W2021235199","https://openalex.org/W2031212222","https://openalex.org/W2035669377","https://openalex.org/W2040760712","https://openalex.org/W2045665292","https://openalex.org/W2050858459","https://openalex.org/W2059403390","https://openalex.org/W2060797027","https://openalex.org/W2068882131","https://openalex.org/W2068887618","https://openalex.org/W2073746011","https://openalex.org/W2081359387","https://openalex.org/W2090079874","https://openalex.org/W2103860452","https://openalex.org/W2114334676","https://openalex.org/W2114850508","https://openalex.org/W2116472408","https://openalex.org/W2125801802","https://openalex.org/W2130479394","https://openalex.org/W2144893180","https://openalex.org/W2148777915","https://openalex.org/W2295598076","https://openalex.org/W2331937820","https://openalex.org/W2413242448","https://openalex.org/W2756641028","https://openalex.org/W2968260576","https://openalex.org/W2999615587","https://openalex.org/W3045355728","https://openalex.org/W3116286104","https://openalex.org/W3177828909","https://openalex.org/W3207488059","https://openalex.org/W3215591662","https://openalex.org/W4200307180","https://openalex.org/W4318323753","https://openalex.org/W4396721167","https://openalex.org/W4396935885","https://openalex.org/W4410530385"],"related_works":[],"abstract_inverted_index":{"Iron-sulfur":[0],"(Fe-S)":[1],"clusters":[2],"are":[3,65],"ubiquitous":[4],"cofactors":[5],"in":[6,40,60,184,198,204],"metalloproteins,":[7],"supporting":[8],"essential":[9],"biological":[10,144],"functions":[11],"such":[12],"as":[13,173,195],"electron":[14],"transfer,":[15],"enzymatic":[16],"catalysis,":[17],"and":[18,37,80,111,165,191,206,254],"metabolic":[19],"regulation.":[20],"Despite":[21],"their":[22,180,201,259],"importance,":[23],"large-scale":[24],"identification":[25],"of":[26,34,137,146,214,222,251],"Fe-S":[27,62,84,99,161,252],"proteins":[28,100,253],"remains":[29],"challenging":[30],"due":[31],"to":[32,97,154],"limitations":[33],"experimental":[35],"methods":[36,151],"inconsistent":[38],"annotations":[39],"existing":[41],"databases.":[42],"To":[43,141],"address":[44],"this,":[45],"we":[46],"introduced":[47],"FeSseqdb,":[48],"a":[49,78,91,245],"curated":[50],"sequence-level":[51],"database":[52],"derived":[53],"from":[54],"the":[55,115,118,129,134,143,220],"Protein":[56],"Data":[57],"Bank":[58],"(PDB),":[59],"which":[61,176],"cluster-containing":[63],"chains":[64],"systematically":[66],"verified":[67],"using":[68,101],"atomic":[69],"coordinates.":[70],"By":[71],"standardizing":[72],"diverse":[73],"ligand":[74],"annotations,":[75],"FeSseqdb":[76],"provides":[77,244],"unified":[79],"reliable":[81],"resource":[82],"for":[83,227,232,247],"protein":[85],"research.":[86],"Building":[87],"on":[88,123],"this":[89],"foundation,":[90],"machine":[92],"learning":[93],"framework":[94],"was":[95],"developed":[96],"predict":[98],"only":[102,226],"sequence-derived":[103],"features,":[104,148],"including":[105],"amino":[106],"acid":[107],"composition,":[108],"cysteine-related":[109],"metrics,":[110],"sequence":[112,139,157],"length.":[113],"Among":[114],"classifiers":[116],"evaluated,":[117],"random":[119],"forest":[120],"model":[121],"trained":[122],"data":[124],"resampled":[125],"with":[126,160,169,179,200,238],"SVMSMOTE":[127],"achieved":[128],"highest":[130],"predictive":[131],"performance,":[132],"highlighting":[133],"discriminative":[135],"power":[136],"simple":[138],"features.":[140],"elucidate":[142],"relevance":[145],"these":[147,215],"explainable":[149],"AI":[150],"were":[152,193],"applied":[153],"identify":[155],"key":[156],"characteristics":[158],"associated":[159],"proteins.":[162],"Cysteine":[163],"frequency":[164],"spatial":[166],"distribution,":[167],"along":[168],"proline":[170],"content,":[171],"emerged":[172],"primary":[174],"contributors,":[175],"is":[177],"consistent":[178],"known":[181,239],"structural":[182],"roles":[183,203],"cluster":[185],"coordination.":[186],"Additionally,":[187],"serine,":[188],"glutamic":[189],"acid,":[190],"arginine":[192],"identified":[194],"secondary":[196],"determinants,":[197],"line":[199],"reported":[202],"redox":[205],"electrostatic":[207],"environments":[208],"surrounding":[209],"metal":[210],"cofactors.":[211],"The":[212],"inclusion":[213],"biologically":[216],"relevant":[217],"features":[218],"demonstrates":[219],"potential":[221],"sequence-based":[223,249],"models":[224],"not":[225],"accurate":[228],"prediction":[229],"but":[230],"also":[231],"uncovering":[233],"functional":[234,260],"insights":[235],"that":[236],"align":[237],"biochemical":[240],"principles.":[241],"This":[242],"approach":[243],"foundation":[246],"large-scale,":[248],"discovery":[250],"supports":[255],"future":[256],"investigations":[257],"into":[258],"diversity":[261],"across":[262],"proteomes.":[263]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2026-06-24T00:00:00"}